transformers 6 huggingface 6 llm 6 rlhf 5 grpo 5 pytorch 4 reinforcement-learning 4 peft 4 dpo 3 unsloth 3 lora 3 transformer 3 direct-preference-optimization 2 grpotrainer 2 supervised-finetuning 2 adapters 2 ppo 2 python 2 safetensors 2 text-generation-inference 2 langchain 2 fine-tuning 2 zephyr 1 faiss 1 preference-data 1 lm-alignment 1 alignment-handbook 1 simple 1 bal-rule 1 deepseek-r1 1 r1-zero 1 reinforcement-learning-with-verifiable-rewards 1 llm-rlhf 1 reward 1 trlx 1 vlm 1 build 1 nanopi 1 nanopi-r1 1 nanopi-r1s 1 openwrt 1 qwen2-5 1 irl 1 odm 1 operational-decision-manager 1 ruleset 1 technical-rule 1 translation 1 verbalization 1 qwen 1 rl 1 sft 1 syntax-tree 1 term-database 1 term-rewriting 1 flan-t5 1 nlp 1 summarization 1 llamacpp 1 mistral 1 rag 1 alpaca 1 large-language-models 1 open-llama 1 polylm 1 qwen2 1 adapter 1 chatgpt 1 gpt 1 gpt-4 1 llama 1